{"id":"W2138441731","doi":"10.1109/ijcnn.1991.155363","title":"Neural-net method for dual subspace pattern recognition","year":2002,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Subspace topology; Hebbian theory; Computer science; Artificial neural network; Artificial intelligence; Dual (grammatical number); Pattern recognition (psychology); Set (abstract data type); Backpropagation; Net (polyhedron); Random subspace method; Layer (electronics); Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008732529,0.00007214098,0.00007042416,0.00002409163,0.0001082201,0.00009565934,0.0002137699,0.00002847025,0.0001185286],"category_scores_gemma":[0.000005868892,0.00006066114,0.00004819637,0.0001713307,0.000008372363,0.0002067907,0.00005303818,0.00005174346,0.0001138794],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005756521,"about_ca_system_score_gemma":0.000001716277,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001651047,"about_ca_topic_score_gemma":0.00001670001,"domain_scores_codex":[0.9993669,0.00002598309,0.0001057962,0.0002505725,0.00007587255,0.0001748769],"domain_scores_gemma":[0.999469,0.0001484772,0.00003738794,0.0002466419,0.00004190473,0.00005654844],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[4.398216e-7,0.00002979514,0.00001925946,0.000002917542,0.000002944103,9.862491e-7,0.00005046345,0.00006874155,0.000323592,0.002311255,0.05189832,0.9452913],"study_design_scores_gemma":[0.0001685877,0.00004616103,0.0002034794,0.000002542694,0.00000380657,0.00001584636,0.000005514572,0.9760949,0.001439718,0.003738357,0.01816385,0.0001172194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002164848,0.00002765707,0.9843693,0.01131088,0.0001198958,0.0002219468,0.000005050285,0.0001605819,0.001619886],"genre_scores_gemma":[0.3664607,0.00003327881,0.6236364,0.005559995,0.0003681625,0.0002369256,0.0000156666,0.00001565746,0.003673267],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9760262,"threshold_uncertainty_score":0.2473689,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06509666865989061,"score_gpt":0.2917495880686889,"score_spread":0.2266529194087983,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}